Exploiting Environment Configurability in Reinforcement Learning


In recent decades, Reinforcement Learning (RL) has emerged as an effective approach to address complex control tasks. In a Markov Decision Process (MDP), the framework typically used, the environment is assumed to be a fixed entity that cannot be altered externally. There are, however, several real-world scenarios in which the environment can be modified to a limited extent. 

This book, Exploiting Environment Configurability in Reinforcement Learning, aims to formalize and study diverse aspects of environment configuration. In a traditional MDP, the agent perceives the state of the environment and performs actions. As a consequence, the environment transitions to a new state and generates a reward signal. The goal of the agent consists of learning a policy, i.e., a prescription of actions that maximize the long-term reward. Although environment configuration arises quite often in real applications, the topic is very little explored in the literature. The contributions in the book are theoretical, algorithmic, and experimental and can be broadly subdivided into three parts. The first part introduces the novel formalism of Configurable Markov Decision Processes (Conf-MDPs) to model the configuration opportunities offered by the environment. The second part of the book focuses on the cooperative Conf-MDP setting and investigates the problem of finding an agent policy and an environment configuration that jointly optimize the long-term reward. The third part addresses two specific applications of the Conf-MDP framework: policy space identification and control frequency adaptation. 

The book will be of interest to all those using RL as part of their work.

Author: Metelli, A.M.
Pages: 376
Binding: softcover
Volume 361 of Frontiers in Artificial Intelligence and Applications
ISBN print: 978-1-64368-362-1
ISBN online: 978-1-64368-363-8

Legal Knowledge and Information Systems


JURIX 2022: The Thirty-fifth Annual Conference, Saarbrücken, Germany, 14-16 December 2022

In recent years, interest within the research community and the legal industry regarding technological advances in legal knowledge representation and processing has been growing. This relates to areas such as computational models of legal reasoning, cybersecurity, privacy, trust and blockchain methods, among other things.

This book presents the proceedings of JURIX 2022, the 35th International Conference on Legal Knowledge and Information Systems, held from 14 –16 December in Saarbrücken, Germany, under the auspices of the Dutch Foundation for Legal Knowledge Based Systems and hosted by Saarland University. The annual JURIX conference has become an international forum for academics and professionals to exchange knowledge and experiences at the intersection of law and artificial intelligence (AI). For this edition, 62 submissions were received from 163 authors in 24 countries. Following a rigorous review process, carried out by a programme committee of 72 experts recognised in the field, 14 submissions were selected for publication as long papers, 22 as short papers and 5 as demo papers, making a total of 41 papers altogether and representing a 22.5% acceptance rate for long papers (66.1% overall). The broad array of topics covered includes argumentation and legal reasoning, legal ontologies and the semantic web, machine and deep learning and natural language processing for legal knowledge extraction, as well as argument mining, translation of legal texts, defeasible logic, legal compliance, explainable AI, alternative dispute resolution, legal drafting and smart contracts.

Providing an overview of recent advances, the book will be of interest to all those working at the interface between the law and AI.

Editors: Francesconi, E., Borges, G., Sorge, C.
Pages: 322
Binding: softcover
Volume 362 of Frontiers in Artificial Intelligence and Applications
ISBN print: 978-1-64368-364-5
ISBN online: 978-1-64368-365-2

Deep Learning with Relational Logic Representations

Deep learning has been used with great success in a number of diverse applications, ranging from image processing to game playing, and the fast progress of this learning paradigm has even been seen as paving the way towards general artificial intelligence. However, the current deep learning models are still principally limited in many ways.

This book, ‘Deep Learning with Relational Logic Representations’, addresses the limited expressiveness of the common tensor-based learning representation used in standard deep learning, by generalizing it to relational representations based in mathematical logic. This is the natural formalism for the relational data omnipresent in the interlinked structures of the Internet and relational databases, as well as for the background knowledge often present in the form of relational rules and constraints. These are impossible to properly exploit with standard neural networks, but the book introduces a new declarative deep relational learning framework called Lifted Relational Neural Networks, which generalizes the standard deep learning models into the relational setting by means of a ‘lifting’ paradigm, known from Statistical Relational Learning. The author explains how this approach allows for effective end-to-end deep learning with relational data and knowledge, introduces several enhancements and optimizations to the framework, and demonstrates its expressiveness with various novel deep relational learning concepts, including efficient generalizations of popular contemporary models, such as Graph Neural Networks.

Demonstrating the framework across various learning scenarios and benchmarks, including computational efficiency, the book will be of interest to all those interested in the theory and practice of advancing representations of modern deep learning architectures.

Author: Šír, G.
Pages: 238
Binding: softcover
Volume 357 of Frontiers in Artificial Intelligence and Applications
ISBN print: 978-1-64368-342-3
ISBN online: 978-1-64368-343-0

Fuzzy Systems and Data Mining VIII


Proceedings of FSDM 2022

Fuzzy logic is vital to applications in the electrical, industrial, chemical and engineering realms, as well as in areas of management and environmental issues. Data mining is indispensible in dealing with big data, massive data, and scalable, parallel and distributed algorithms.

This book presents papers from FSDM 2022, the 8th International Conference on Fuzzy Systems and Data Mining. The conference, originally scheduled to take place in Xiamen, China, was held fully online from 4 to 7 November 2022, due to ongoing restrictions connected with the COVID-19 pandemic. This year, FSDM received 196 submissions, of which 47 papers were ultimately selected for presentation and publication after a thorough review process, taking into account novelty, and the breadth and depth of research themes falling under the scope of FSDM. This resulted in an acceptance rate of 23.97%. Topics covered include fuzzy theory, algorithms and systems, fuzzy applications, data mining and the interdisciplinary field of fuzzy logic and data mining.

Offering an overview of current research and developments in fuzzy logic and data mining, the book will be of interest to all those working in the field of data science.

Editor: Tallón-Ballesteros, A.J.
Pages: 438
Binding: softcover
Volume 358 of Frontiers in Artificial Intelligence and Applications
ISBN print: 978-1-64368-346-1
ISBN online: 978-1-64368-347-8

Advanced Tools and Methods for Treewidth-Based Problem Solving

This book, Advanced Tools and Methods for Treewidth-Based Problem Solving, contains selected results from the author’s PhD studies, which were carried out from 2015 to 2021. For his PhD thesis, Markus Hecher received the EurAI Dissertation Award 2021 and the GI Dissertation Award 2021, amongst others.

The aim of the book is to present a new toolkit for using the structural parameter of treewidth to solve problems in knowledge representation and reasoning (KR) and artificial intelligence (AI), thereby establishing both theoretical upper and lower bounds, as well as methods to deal with treewidth efficiently in practice. The key foundations outlined in the book provide runtime lower bounds – under reasonable assumptions in computational complexity – for evaluating quantified Boolean formulas and logic programs which match the known upper bounds already published in 2004 and 2009.

The general nature of the developed tools and techniques means that a wide applicability beyond the selected problems and formalisms tackled in the book is anticipated, and it is hoped that the book will serve as a starting point for future theoretical and practical investigations, which will no doubt establish further results and gain deeper insights.

Author: Hecher, M.
Pages: 250
Binding: softcover
Volume 359 of Frontiers in Artificial Intelligence and Applications
ISBN print: 978-1-64368-344-7
ISBN online: 978-1-64368-345-4

Augmenting Human Intellect


Proceedings of the First International Conference on Hybrid Human-Artificial Intelligence

Hybrid human-artificial intelligence is a new research area concerned with all aspects of AI systems that assist humans, and vice versa. The emphasis is on the need for adaptive, collaborative, responsible, interactive and human-centered artificial intelligence systems that can leverage human strengths and compensate for human weaknesses while taking into account social, ethical and legal considerations. The challenge is to develop robust, trustworthy AI systems that can ‘understand’ humans, adapt to complex real-world environments and interact appropriately in a variety of social settings.

This book presents the proceedings of the 1st International Conference on Hybrid Human-Artificial Intelligence (HHAI2022), held in Amsterdam, The Netherlands, from 13 -17June 2022. HHAI2022 was the first international conference focusing on the study of AI systems that amplify rather than replace human intelligence by cooperating synergistically, proactively, responsibly and purposefully with humans. Scholars from the fields of AI, human computer interaction, cognitive and social sciences, computer science, philosophy, and others were invited to submit their best original work on hybrid human-artificial intelligence. The book contains 24 main-track papers, 17 poster and demo papers, and 1 Hackathon paper, selected from a total of 96 submissions, and topics covered include human-AI interaction and collaboration, co-learning and co-creation; learning, reasoning and planning with humans and machines in the loop; integration of learning and reasoning; law and policy challenges around human-centered AI systems; and societal awareness of AI.

The book provides an up-to-date overview of this novel and timely field of study, and will be of interest to all those working with aspects of artificial intelligence, in whatever field.

Editors: Schlobach, S., Pérez-Ortiz, M., Tielman, M.
Pages: 346
Binding: softcover
Volume 354 of Frontiers in Artificial Intelligence and Applications
ISBN print: 978-1-64368-308-9
ISBN online: 978-1-64368-309-6

Artificial Intelligence Research and Development


Proceedings of the 24th International Conference of the Catalan Association for Artificial Intelligence

Artificial intelligence has become an integral part of all our lives. Development is rapid in this exciting and far-reaching field, and keeping up to date with the latest research and innovation is crucial to all those working with the technology.

This book presents the proceedings of the 24th edition of CCIA, the International Conference of the Catalan Association for Artificial Intelligence, held in Sitges, Spain, from 19 – 21 October 2022. This annual event serves as a meeting point not only for researchers in AI from the Catalan speaking territories (southern France, Catalonia, Valencia, the Balearic Islands and Alghero in Italy) but for researchers from around the world. The programme committee received 59 submissions, from which the 26 long papers and 23 short papers selected for presentation at the conference by the 62 experts who make up the committee are included here. The book is divided into the following sections: combinatorial problem solving and logics for artificial intelligence; sentiment analysis and tekst analysis; data science, recommender systems and decision support systems; machine learning; computer vision; and explainability and argumentation. This book also includes an abstract of the invited talk given by Prof. Fosca Giannotti.

Providing a comprehensive overview of research and development, this book will be of interest to all those working in the field of Artificial Intelligence.

Editors: Cortés, A., Grimaldo, F., Flaminio, T.
Pages: 388
Binding: softcover
Volume 356 of Frontiers in Artificial Intelligence and Applications
ISBN print: 978-1-64368-326-3
ISBN online: 978-1-64368-327-0

Modern Management based on Big Data III


Proceedings of MMBD 2022

Data is the basic ingredient of all Big Data applications, and Big Data technologies are constantly deploying new strategies to maximise efficiency and reduce the time taken to process information.

This book presents the proceedings of MMBD2022, the third edition of the conference series Modern Management based on Big Data (MMBD). The conference was originally scheduled to take place from 15 to 18 August 2022 in Seoul, South Korea, but was changed to a virtual event on the same dates. Some 200 submissions were received for presentation at the conference, 52 of which were ultimately accepted after exhaustive review by members of the programme committee and peer-reviewers, who took into account the breadth and depth of the research topics and the scope of MMBD. Topics covered include data analytics, modelling, technologies and visualization, architectures for parallel processing systems, data mining tools and techniques, machine learning algorithms, and big data for engineering applications. There are also papers covering modern management, including topics such as strategy, decision making, manufacturing and logistics-based systems, engineering economy, information systems and law-based information treatment, and papers from a special session covering big data in manufacturing, retail, healthcare, accounting, banking, education, global trading, and e-commerce. Big data analysis and emerging applications were popular topics.

The book includes many innovative and original ideas, as well as results of general significance, all supported by clear and rigorous reasoning and compelling evidence and methods, and will be of interest to all those working with Big Data.

Editor: Tallón-Ballesteros, A.J
Pages: 496
Binding: softcover
Volume 352 of Frontiers in Artificial Intelligence and Applications
ISBN print: 978-1-64368-300-3
ISBN online: 978-1-64368-301-0

Computational Models of Argument


Proceedings of COMMA 2022

This volume presents papers from the Third Conference on Computational Models of Argument, held in September 2010 in Desanzano del Garda, Italy.

Argumentation has been the subject of research in a number of different fields where a solution is sought for the many problems encountered in the knowledge representation and reasoning area of artificial intelligence. The goal is the development of applications using strategies akin to the commonsense approach applied by humans. In recent years such practical applications of basic research results have been the subject of increasing attention, especially within the autonomous agents and multiagent systems community. To answer the need for a forum where advances in the field could be discussed in a specialised manner by members of the argumentation community, the first conference in this series was held in 2006 at the University of Liverpool. The success of both the first and the subsequent second conference, held in Toulouse in 2008, has established this conference as a biennial event.

The call for papers for the third conference resulted in the submission of 67 papers, of which the 35 full papers and five short papers selected are presented here, along with two invited papers from prof. Gerhard Brewka and prof. Douglas Walton. Subjects covered range from formal models of argumentation and the relevant theoretical questions, through algorithms and computational complexity issues, to the use of argumentation in several application domains.

Overall this volume provides an up to date view of this important research field and will be of interest to all those involved in the use and development of artificial intelligence systems.

Editors: Toni, F., Polberg, S., Booth, R., Caminada, M., Kido, H.
Pages: 398
Binding: softcover
Volume 353 of Frontiers in Artificial Intelligence and Applications
ISBN print: 978-1-64368-306-5
ISBN online: 978-1-64368-307-2

PAIS 2022


11th Conference on Prestigious Applications of Artificial Intelligence, 25 July 2022, Vienna, Austria (co-located with IJCAI-ECAI 2022)

Artificial Intelligence (AI) is a central topic in contemporary computer science; one which has enabled many groundbreaking developments that have significantly influenced our society. Not only has it proved to be of fundamental importance in areas such as medicine, biology, economics, philosophy, linguistics, psychology and engineering, but it has also had a significant impact in a number of fields, including e-commerce, tourism, e-government, national security, manufacturing and other economic sectors.

This book contains the proceedings of PAIS 2022, the 11th Conference on Prestigious Applications of Artificial Intelligence, held in Vienna, Austria, on 25 July 2022 as a satellite event of IJCAI-ECAI 2022. The PAIS conference invites papers describing innovative applications of AI techniques to real-world systems and problems, and aims to provide a forum for academic and industrial researchers and practitioners to share their experience and insight on the applicability, development and deployment of intelligent systems. A total of 18 full-paper submissions and 4 extended-abstract submissions were received for the 2022 conference, of which 10 full papers and 3 extended abstracts were accepted after rigorous peer review. The topics covered range from autonomous navigation, air traffic control and satellite management to the optimization of industrial processes and human-in-the-loop applications.

The book will be of interest to all those whose work involves the innovative application of AI techniques to real-world situations.

Editors: Passerini, A., Schiex, T.
Pages: 170
Binding: softcover
Volume 351 of Frontiers in Artificial Intelligence and Applications
ISBN print: 978-1-64368-294-5
ISBN online: 978-1-64368-295-2

Pages

Subscribe to Frontiers in Artificial Intelligence and Applications (FAIA) RSS